dalance/amber
A code search / replace tool
565
Generated Behavioral Tests
94.9%
Best Score
Claude Opus 5 (xhigh)
Results by Model
Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details
Per-Model Results
21 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
Claude Opus 5 (xhigh) | 94.9% | $43.90 | 280 | trace → |
| 2 | |
Claude Opus 4.8 (xhigh) | 89.4% | $28.09 | 164 | trace → |
| 3 |  |
GPT-5.6 Sol (xhigh) | 86.9% | $4.37 | 47 | trace → |
| 4 | |
Claude Opus 4.7 (xhigh) | 74.3% | $16.71 | 329 | trace → |
| 5 | |
GPT 5.5 | 72.6% | $0.78 | 20 | trace → |
| 6 | |
GPT-5.6 Sol | 71.9% | $0.88 | 18 | trace → |
| 7 |  |
Gemini 3.7 Flash | 71.9% | $0.72 | 91 | trace → |
| 8 | |
Gemini 3.5 Flash | 71.2% | $2.36 | 116 | trace → |
| 9 | |
Claude Sonnet 4.6 | 71.0% | $23.27 | 507 | trace → |
| 10 |  |
GLM-5.2 | 69.6% | $16.12 | 162 | trace → |
| 11 | |
Claude Opus 4.6 | 68.7% | $14.47 | 329 | trace → |
| 12 | |
Claude Opus 4.7 | 67.8% | $2.97 | 96 | trace → |
| 13 | |
GPT 5.4 | 67.8% | $4.75 | 1,000 | trace → |
| 14 | |
Gemini 3 Flash | 64.1% | $0.30 | 126 | trace → |
| 15 | |
Gemini 3.6 Flash | 54.3% | $3.60 | 154 | trace → |
| 16 | |
Gemini 3.1 Pro | 52.9% | $0.93 | 91 | trace → |
| 17 | |
Claude Haiku 4.5 | 46.4% | $0.33 | 81 | trace → |
| 18 | |
GPT 5.5 (xhigh) | 23.2% | $4.70 | 77 | trace → |
| 19 | |
GPT 5.5 (high) | 22.3% | $2.07 | 44 | trace → |
| 20 | |
GPT 5 mini | 12.4% | $0.01 | 8 | trace → |
| 21 | |
GPT 5.4 mini | 3.4% | $0.02 | 7 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run